© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 3914
    Prev
    Next
    INDEX
    Explanations

    terms related to technical specifications and functions of software and hardware systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ="@+
    -0.50
    Occurred
    -0.49
    HasAnnotation
    -0.48
     tán
    -0.47
     ihres
    -0.46
     Yet
    -0.45
    onekana
    -0.44
    Yet
    -0.43
    delwed
    -0.43
     polvere
    -0.43
    POSITIVE LOGITS
    の場合
    0.87
     BoxFit
    0.78
    の場合は
    0.77
    mappedBy
    0.70
     يتيمه
    0.68
    に限
    0.65
    する場合
    0.65
    RenderAtEndOf
    0.62
    した場合
    0.61
    czegó
    0.61
    Activations Density 1.154%

    No Known Activations